# SuperCosmos 2.0 Heavy

> The deliberate SuperCosmos 2.0 effort. Thinks longest and writes the longest answers, for the hardest problems.

Heavy spends the most effort per step and writes the longest answers. It's slower and costs more, and it's the effort to reach for when the other two can't crack a problem.

| | |
| --- | --- |
| Display name | SuperCosmos 2.0 Heavy |
| Model id | `supercosmos-2-heavy` |
| Model | SuperCosmos 2.0: 1T parameters |
| Context window | Up to 1M tokens (1,048,576) |
| Max output tokens | 49,152 |
| Input | Text, images and files |
| Agent API | `"tier": "heavy"` |
| Input price | $2.60 per 1M tokens |
| Output price | $6.40 per 1M tokens |
| Long context | Long-context input above 262K tokens: 1.5× |

## Good fits

- Hard bugs: race conditions, memory issues, flaky tests
- Large builds and migrations
- Architecture and design reviews
- Long documents that need careful reasoning

## Move up when

Heavy is the deepest effort. If it still struggles, split the task into smaller steps.

<Tip>
Heavy is rarely the right default. Use `auto` or Flash for most runs and send only the hard ones to Heavy.
</Tip>
